BilalMuftuoglu commited on
Commit
4b599c4
1 Parent(s): fe45c20

Model save

Browse files
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-base-distilled-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: deit-base-distilled-patch16-224-hasta-85-fold3
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.7272727272727273
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # deit-base-distilled-patch16-224-hasta-85-fold3
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 2.2286
36
+ - Accuracy: 0.7273
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 100
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 1 | 0.8686 | 0.6364 |
71
+ | No log | 2.0 | 2 | 0.7871 | 0.7273 |
72
+ | No log | 3.0 | 3 | 0.7116 | 0.7273 |
73
+ | No log | 4.0 | 4 | 0.7585 | 0.7273 |
74
+ | No log | 5.0 | 5 | 0.9216 | 0.7273 |
75
+ | No log | 6.0 | 6 | 1.0848 | 0.7273 |
76
+ | No log | 7.0 | 7 | 1.1931 | 0.7273 |
77
+ | No log | 8.0 | 8 | 1.2543 | 0.7273 |
78
+ | No log | 9.0 | 9 | 1.3098 | 0.7273 |
79
+ | 0.2667 | 10.0 | 10 | 1.3979 | 0.7273 |
80
+ | 0.2667 | 11.0 | 11 | 1.4209 | 0.7273 |
81
+ | 0.2667 | 12.0 | 12 | 1.4302 | 0.7273 |
82
+ | 0.2667 | 13.0 | 13 | 1.4202 | 0.7273 |
83
+ | 0.2667 | 14.0 | 14 | 1.3569 | 0.7273 |
84
+ | 0.2667 | 15.0 | 15 | 1.3033 | 0.7273 |
85
+ | 0.2667 | 16.0 | 16 | 1.3414 | 0.7273 |
86
+ | 0.2667 | 17.0 | 17 | 1.4312 | 0.7273 |
87
+ | 0.2667 | 18.0 | 18 | 1.6063 | 0.7273 |
88
+ | 0.2667 | 19.0 | 19 | 1.7308 | 0.7273 |
89
+ | 0.1296 | 20.0 | 20 | 1.7541 | 0.7273 |
90
+ | 0.1296 | 21.0 | 21 | 1.7183 | 0.7273 |
91
+ | 0.1296 | 22.0 | 22 | 1.6395 | 0.7273 |
92
+ | 0.1296 | 23.0 | 23 | 1.6197 | 0.7273 |
93
+ | 0.1296 | 24.0 | 24 | 1.6525 | 0.7273 |
94
+ | 0.1296 | 25.0 | 25 | 1.7183 | 0.7273 |
95
+ | 0.1296 | 26.0 | 26 | 1.7120 | 0.7273 |
96
+ | 0.1296 | 27.0 | 27 | 1.6748 | 0.7273 |
97
+ | 0.1296 | 28.0 | 28 | 1.5840 | 0.7273 |
98
+ | 0.1296 | 29.0 | 29 | 1.5963 | 0.7273 |
99
+ | 0.0834 | 30.0 | 30 | 1.7016 | 0.7273 |
100
+ | 0.0834 | 31.0 | 31 | 1.7780 | 0.7273 |
101
+ | 0.0834 | 32.0 | 32 | 1.7943 | 0.7273 |
102
+ | 0.0834 | 33.0 | 33 | 1.7993 | 0.7273 |
103
+ | 0.0834 | 34.0 | 34 | 1.7873 | 0.7273 |
104
+ | 0.0834 | 35.0 | 35 | 1.8196 | 0.7273 |
105
+ | 0.0834 | 36.0 | 36 | 1.9190 | 0.7273 |
106
+ | 0.0834 | 37.0 | 37 | 2.0467 | 0.7273 |
107
+ | 0.0834 | 38.0 | 38 | 2.1647 | 0.7273 |
108
+ | 0.0834 | 39.0 | 39 | 2.2634 | 0.7273 |
109
+ | 0.0441 | 40.0 | 40 | 2.3170 | 0.7273 |
110
+ | 0.0441 | 41.0 | 41 | 2.3263 | 0.7273 |
111
+ | 0.0441 | 42.0 | 42 | 2.2991 | 0.7273 |
112
+ | 0.0441 | 43.0 | 43 | 2.2792 | 0.7273 |
113
+ | 0.0441 | 44.0 | 44 | 2.2572 | 0.7273 |
114
+ | 0.0441 | 45.0 | 45 | 2.2751 | 0.7273 |
115
+ | 0.0441 | 46.0 | 46 | 2.3103 | 0.7273 |
116
+ | 0.0441 | 47.0 | 47 | 2.3325 | 0.7273 |
117
+ | 0.0441 | 48.0 | 48 | 2.3259 | 0.7273 |
118
+ | 0.0441 | 49.0 | 49 | 2.2974 | 0.7273 |
119
+ | 0.0437 | 50.0 | 50 | 2.2312 | 0.7273 |
120
+ | 0.0437 | 51.0 | 51 | 2.1638 | 0.7273 |
121
+ | 0.0437 | 52.0 | 52 | 2.0963 | 0.7273 |
122
+ | 0.0437 | 53.0 | 53 | 2.0074 | 0.7273 |
123
+ | 0.0437 | 54.0 | 54 | 1.9069 | 0.7273 |
124
+ | 0.0437 | 55.0 | 55 | 1.8899 | 0.7273 |
125
+ | 0.0437 | 56.0 | 56 | 1.9432 | 0.7273 |
126
+ | 0.0437 | 57.0 | 57 | 2.0307 | 0.7273 |
127
+ | 0.0437 | 58.0 | 58 | 2.1621 | 0.7273 |
128
+ | 0.0437 | 59.0 | 59 | 2.2470 | 0.7273 |
129
+ | 0.04 | 60.0 | 60 | 2.3281 | 0.7273 |
130
+ | 0.04 | 61.0 | 61 | 2.3529 | 0.7273 |
131
+ | 0.04 | 62.0 | 62 | 2.3491 | 0.7273 |
132
+ | 0.04 | 63.0 | 63 | 2.3534 | 0.7273 |
133
+ | 0.04 | 64.0 | 64 | 2.3541 | 0.7273 |
134
+ | 0.04 | 65.0 | 65 | 2.3474 | 0.7273 |
135
+ | 0.04 | 66.0 | 66 | 2.3363 | 0.7273 |
136
+ | 0.04 | 67.0 | 67 | 2.3193 | 0.7273 |
137
+ | 0.04 | 68.0 | 68 | 2.3144 | 0.7273 |
138
+ | 0.04 | 69.0 | 69 | 2.2847 | 0.7273 |
139
+ | 0.0232 | 70.0 | 70 | 2.2488 | 0.7273 |
140
+ | 0.0232 | 71.0 | 71 | 2.2175 | 0.7273 |
141
+ | 0.0232 | 72.0 | 72 | 2.1898 | 0.7273 |
142
+ | 0.0232 | 73.0 | 73 | 2.1797 | 0.7273 |
143
+ | 0.0232 | 74.0 | 74 | 2.1829 | 0.7273 |
144
+ | 0.0232 | 75.0 | 75 | 2.1806 | 0.7273 |
145
+ | 0.0232 | 76.0 | 76 | 2.1685 | 0.7273 |
146
+ | 0.0232 | 77.0 | 77 | 2.1505 | 0.7273 |
147
+ | 0.0232 | 78.0 | 78 | 2.1548 | 0.7273 |
148
+ | 0.0232 | 79.0 | 79 | 2.1650 | 0.7273 |
149
+ | 0.0243 | 80.0 | 80 | 2.1961 | 0.7273 |
150
+ | 0.0243 | 81.0 | 81 | 2.2283 | 0.7273 |
151
+ | 0.0243 | 82.0 | 82 | 2.2619 | 0.7273 |
152
+ | 0.0243 | 83.0 | 83 | 2.2783 | 0.7273 |
153
+ | 0.0243 | 84.0 | 84 | 2.2796 | 0.7273 |
154
+ | 0.0243 | 85.0 | 85 | 2.2780 | 0.7273 |
155
+ | 0.0243 | 86.0 | 86 | 2.2769 | 0.7273 |
156
+ | 0.0243 | 87.0 | 87 | 2.2655 | 0.7273 |
157
+ | 0.0243 | 88.0 | 88 | 2.2584 | 0.7273 |
158
+ | 0.0243 | 89.0 | 89 | 2.2419 | 0.7273 |
159
+ | 0.0301 | 90.0 | 90 | 2.2299 | 0.7273 |
160
+ | 0.0301 | 91.0 | 91 | 2.2151 | 0.7273 |
161
+ | 0.0301 | 92.0 | 92 | 2.2038 | 0.7273 |
162
+ | 0.0301 | 93.0 | 93 | 2.1956 | 0.7273 |
163
+ | 0.0301 | 94.0 | 94 | 2.1946 | 0.7273 |
164
+ | 0.0301 | 95.0 | 95 | 2.2012 | 0.7273 |
165
+ | 0.0301 | 96.0 | 96 | 2.2079 | 0.7273 |
166
+ | 0.0301 | 97.0 | 97 | 2.2151 | 0.7273 |
167
+ | 0.0301 | 98.0 | 98 | 2.2219 | 0.7273 |
168
+ | 0.0301 | 99.0 | 99 | 2.2261 | 0.7273 |
169
+ | 0.0154 | 100.0 | 100 | 2.2286 | 0.7273 |
170
+
171
+
172
+ ### Framework versions
173
+
174
+ - Transformers 4.41.0
175
+ - Pytorch 2.3.0+cu121
176
+ - Datasets 2.19.1
177
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7d5ac271677abd4c11c14fe0cd658c98645d94f4ff40803eeb898b5e36c878d
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782d9ef963bdc27e29737a91427578282f6f5ec35866d998040a4a1f32cad21a
3
  size 343233492
runs/May22_16-08-52_927069b479b5/events.out.tfevents.1716394133.927069b479b5.252.40 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0e5613fee535b9f0b3cd2bb26a8a0ccbba2627fe0dcd52c191d1690991a486b
3
- size 37625
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a19c2b1572fd94b321e1feb4f0b822bbe78399244a841e6a68f1e11ed2e145f4
3
+ size 39131